hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From stack <st...@duboce.net>
Subject Re: Hosting a new web app on Hadoop?
Date Fri, 07 Mar 2008 18:14:43 GMT
Your biggest problem at the moment will likely be performance.  Our 
current numbers are not the best.  See the base of this page: 
http://wiki.apache.org/hadoop/Hbase/PerformanceEvaluation  Related, if 
your live table is concurrently being loaded, there will be periods 
during which client will not be able to read data from a region while 
its being split and redeployed.  We need to do some work to add an 
express lane to minimize this down time (We're talking between 1-2 
seconds but it could be as bad as a couple of minutes at an extreme 
dependent on how hard your servers are working).  Also, HBASE-80 is 
about adding a cache of hot cells.  Its not implemented yet but 
shouldn't be too hard to add.  You'd probably need this servicing users 
real-time.

St.Ack


Charlie O'Keefe wrote:
> It seems like I've seen a lot of mentions of running large data analysis
> jobs on Hadoop clusters, but I can't recall reading anything about hosting a
> website on a Hadoop cluster.
>
> I'm just starting to learn about this project but my reaction to reading
> about Hadoop is, "Hey, I'm designing a web application and I'm concerned
> that by using a mysql backend, it will be a challenge should I need to scale
> it. Hey, here's a project that is designed to scale elastically on computing
> clusters, and it includes both a scalable execution environment and a
> scalable database! Why not skip mysql and design my backend around HBase?"
>
> So how about it? I'd be interested in hearing from someone with some
> expertise in Hadoop. Does this idea make sense? Or is there something about
> Hadoop that makes it less than ideal for a new web application project that
> thinks it might scale to lots of data and users?
>
> I am also very curious about best practices for schema design (or whatever
> the HBase equivalent of a schema is), and how best to handle situations in
> which there are many complex relationships between the entities being
> represented.
> Thanks for any help!
>
> Charlie
>
>   


Mime
View raw message